Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 15128
    Prev
    Next
    INDEX
    Explanations

    phrases related to physics concepts, specifically related to properties of photons and measurements in quantum mechanics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to quantum mechanics and measurement uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pees
    -0.89
    ebook
    -0.83
    eks
    -0.80
    projects
    -0.75
    amera
    -0.74
    Americans
    -0.74
    cigarettes
    -0.73
    adobe
    -0.73
     Learns
    -0.71
    uggets
    -0.69
    POSITIVE LOGITS
     symmetry
    1.15
     entropy
    1.15
     coupling
    1.14
     curv
    1.13
     decay
    1.10
     dependence
    1.07
     pert
    1.05
     instability
    1.05
     constraint
    1.03
     interaction
    1.00
    Activations Density 0.225%

    No Known Activations